A key component in autonomous vehicle and fast triggering systems, learn how FPGAs do real-time DNN inference in this hands-on course. Topics include:
- Model compression and quantization
- High-level synthesis
- Firmware implementation
- Model acceleration on cloud FPGAs
The class is given by Dr. Jennifer Ngadiuba (CERN) and Dr. Dylan Rankin (MIT) and consists of half a day of lectures as well as a hands-on sessions.
You'll learn how to compress and synthesise your own TensorFlow model, as well as implement it on a Xilinx FPGA on the Amazon cloud.
The course is targeted at PhD, Postdocs and Professors, but others will be allowed to participate if there are available places.
The lectures and hands-on session will take place at the UZH Irchel Campus in the Physik Institut (building 36)
All course material can be found as attachments to the timetable, or at
https://github.com/FPGA4HEP/course_material
Upload your plot here:
https://cernbox.cern.ch/index.php/s/70rnEFKLh4dU37m
Organizers:
Thea Aarrestad (UZH)
Jennifer Ngadiuba (CERN)
Dylan Rankin (MIT)
Maurizio Pierini (CERN)
Ben Kilminster (UZH)
